Discrete wavelet transform based seizure detection in newborns EEG signals

Pega Zarjam, Mostefa Mesbah

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

This paper proposes a novel method for detecting newborns seizure events from electroencephalogram (EEG) data. The detection scheme is based on the discrete wavelet transform (DWT) of the EEG signals. The number of zero-crossings, the average distance between adjacent zero-crossings, the number of extrema, and the average distance between adjacent extrema of the wavelet coefficients (WCs) of certain scales are extracted to form a feature set. The extracted feature set is then fed to an artificial neural network (ANN) classifier to organize the EEG signals into seizure and non- seizure activities. In this study, the training and test sets were obtained from EEG data acquired from 1 and 5 other neonates, respectively, with ages ranging from 2 days to 2 weeks. The obtained results show that on the average 95% of the EEG seizures were detected by the proposed scheme.

Original languageEnglish
Title of host publicationProceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003
PublisherIEEE Computer Society
Pages459-462
Number of pages4
Volume2
ISBN (Print)0780379462, 9780780379466
DOIs
Publication statusPublished - 2003
Event7th International Symposium on Signal Processing and Its Applications, ISSPA 2003 - Paris, France
Duration: Jul 1 2003Jul 4 2003

Other

Other7th International Symposium on Signal Processing and Its Applications, ISSPA 2003
CountryFrance
CityParis
Period7/1/037/4/03

Fingerprint

Discrete wavelet transforms
Electroencephalography
Classifiers
Neural networks

ASJC Scopus subject areas

  • Signal Processing

Cite this

Zarjam, P., & Mesbah, M. (2003). Discrete wavelet transform based seizure detection in newborns EEG signals. In Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003 (Vol. 2, pp. 459-462). [1224913] IEEE Computer Society. https://doi.org/10.1109/ISSPA.2003.1224913

Discrete wavelet transform based seizure detection in newborns EEG signals. / Zarjam, Pega; Mesbah, Mostefa.

Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003. Vol. 2 IEEE Computer Society, 2003. p. 459-462 1224913.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zarjam, P & Mesbah, M 2003, Discrete wavelet transform based seizure detection in newborns EEG signals. in Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003. vol. 2, 1224913, IEEE Computer Society, pp. 459-462, 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003, Paris, France, 7/1/03. https://doi.org/10.1109/ISSPA.2003.1224913
Zarjam P, Mesbah M. Discrete wavelet transform based seizure detection in newborns EEG signals. In Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003. Vol. 2. IEEE Computer Society. 2003. p. 459-462. 1224913 https://doi.org/10.1109/ISSPA.2003.1224913
Zarjam, Pega ; Mesbah, Mostefa. / Discrete wavelet transform based seizure detection in newborns EEG signals. Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003. Vol. 2 IEEE Computer Society, 2003. pp. 459-462
@inproceedings{ea9273c350da47639040750f2cc0ffbb,
title = "Discrete wavelet transform based seizure detection in newborns EEG signals",
abstract = "This paper proposes a novel method for detecting newborns seizure events from electroencephalogram (EEG) data. The detection scheme is based on the discrete wavelet transform (DWT) of the EEG signals. The number of zero-crossings, the average distance between adjacent zero-crossings, the number of extrema, and the average distance between adjacent extrema of the wavelet coefficients (WCs) of certain scales are extracted to form a feature set. The extracted feature set is then fed to an artificial neural network (ANN) classifier to organize the EEG signals into seizure and non- seizure activities. In this study, the training and test sets were obtained from EEG data acquired from 1 and 5 other neonates, respectively, with ages ranging from 2 days to 2 weeks. The obtained results show that on the average 95{\%} of the EEG seizures were detected by the proposed scheme.",
author = "Pega Zarjam and Mostefa Mesbah",
year = "2003",
doi = "10.1109/ISSPA.2003.1224913",
language = "English",
isbn = "0780379462",
volume = "2",
pages = "459--462",
booktitle = "Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Discrete wavelet transform based seizure detection in newborns EEG signals

AU - Zarjam, Pega

AU - Mesbah, Mostefa

PY - 2003

Y1 - 2003

N2 - This paper proposes a novel method for detecting newborns seizure events from electroencephalogram (EEG) data. The detection scheme is based on the discrete wavelet transform (DWT) of the EEG signals. The number of zero-crossings, the average distance between adjacent zero-crossings, the number of extrema, and the average distance between adjacent extrema of the wavelet coefficients (WCs) of certain scales are extracted to form a feature set. The extracted feature set is then fed to an artificial neural network (ANN) classifier to organize the EEG signals into seizure and non- seizure activities. In this study, the training and test sets were obtained from EEG data acquired from 1 and 5 other neonates, respectively, with ages ranging from 2 days to 2 weeks. The obtained results show that on the average 95% of the EEG seizures were detected by the proposed scheme.

AB - This paper proposes a novel method for detecting newborns seizure events from electroencephalogram (EEG) data. The detection scheme is based on the discrete wavelet transform (DWT) of the EEG signals. The number of zero-crossings, the average distance between adjacent zero-crossings, the number of extrema, and the average distance between adjacent extrema of the wavelet coefficients (WCs) of certain scales are extracted to form a feature set. The extracted feature set is then fed to an artificial neural network (ANN) classifier to organize the EEG signals into seizure and non- seizure activities. In this study, the training and test sets were obtained from EEG data acquired from 1 and 5 other neonates, respectively, with ages ranging from 2 days to 2 weeks. The obtained results show that on the average 95% of the EEG seizures were detected by the proposed scheme.

UR - http://www.scopus.com/inward/record.url?scp=60349123665&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=60349123665&partnerID=8YFLogxK

U2 - 10.1109/ISSPA.2003.1224913

DO - 10.1109/ISSPA.2003.1224913

M3 - Conference contribution

SN - 0780379462

SN - 9780780379466

VL - 2

SP - 459

EP - 462

BT - Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003

PB - IEEE Computer Society

ER -